Intelligent Rolling Bearing Fault Diagnosis Method Using Symmetrized Dot Pattern Images and CBAM-DRN
Rolling bearings are a vital component of mechanical equipment. It is crucial to implement rolling bearing fault diagnosis research to guarantee the stability of the long-term action of mechanical equipment. Conversion of rolling bearing vibration signals into images for fault diagnosis research has...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/24/9954 |
| _version_ | 1797455330371698688 |
|---|---|
| author | Wei Cui Guoying Meng Tingxi Gou Aiming Wang Rui Xiao Xinge Zhang |
| author_facet | Wei Cui Guoying Meng Tingxi Gou Aiming Wang Rui Xiao Xinge Zhang |
| author_sort | Wei Cui |
| collection | DOAJ |
| description | Rolling bearings are a vital component of mechanical equipment. It is crucial to implement rolling bearing fault diagnosis research to guarantee the stability of the long-term action of mechanical equipment. Conversion of rolling bearing vibration signals into images for fault diagnosis research has been a practical diagnostic approach. The current paper presents a rolling bearing fault diagnosis method using symmetrized dot pattern (SDP) images and a deep residual network with convolutional block attention module (CBAM-DRN). The rolling bearing vibration signal is first visualized and transformed into an SDP image with distinct fault characteristics. Then, CBAM-DRN is utilized to derive characteristics directly and detect faults from the input SDP images. In order to prevent conventional time-frequency images from being limited by their inherent flaws and avoid missing the fault features, the SDP technique is employed to convert vibration signals into images for visualization. DRN enables adequate extraction of rolling bearing fault characteristics and prevents training difficulties and gradient vanishing in deep level networks. CBAM assists the diagnostic model in concentrating on the image’s more distinctive parts and preventing the interference of non-featured parts. Finally, the method’s validity was tested with a composite fault dataset of motor bearings containing multiple loads and fault diameters. The experimental results reflect that the presented approach can attain a diagnostic precision of over 99% and good stability and generalization. |
| first_indexed | 2024-03-09T15:51:54Z |
| format | Article |
| id | doaj.art-be6b1c68a9874986a1a9d26f644f1ff6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T15:51:54Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-be6b1c68a9874986a1a9d26f644f1ff62023-11-24T17:58:06ZengMDPI AGSensors1424-82202022-12-012224995410.3390/s22249954Intelligent Rolling Bearing Fault Diagnosis Method Using Symmetrized Dot Pattern Images and CBAM-DRNWei Cui0Guoying Meng1Tingxi Gou2Aiming Wang3Rui Xiao4Xinge Zhang5School of Mechanical Electronic & Information Engineering, China University of Mining & Technology (Beijing), Beijing 100083, ChinaSchool of Mechanical Electronic & Information Engineering, China University of Mining & Technology (Beijing), Beijing 100083, ChinaSchool of Mechanical Electronic & Information Engineering, China University of Mining & Technology (Beijing), Beijing 100083, ChinaSchool of Mechanical Electronic & Information Engineering, China University of Mining & Technology (Beijing), Beijing 100083, ChinaSchool of Mechanical Electronic & Information Engineering, China University of Mining & Technology (Beijing), Beijing 100083, ChinaSchool of Mechanical Electronic & Information Engineering, China University of Mining & Technology (Beijing), Beijing 100083, ChinaRolling bearings are a vital component of mechanical equipment. It is crucial to implement rolling bearing fault diagnosis research to guarantee the stability of the long-term action of mechanical equipment. Conversion of rolling bearing vibration signals into images for fault diagnosis research has been a practical diagnostic approach. The current paper presents a rolling bearing fault diagnosis method using symmetrized dot pattern (SDP) images and a deep residual network with convolutional block attention module (CBAM-DRN). The rolling bearing vibration signal is first visualized and transformed into an SDP image with distinct fault characteristics. Then, CBAM-DRN is utilized to derive characteristics directly and detect faults from the input SDP images. In order to prevent conventional time-frequency images from being limited by their inherent flaws and avoid missing the fault features, the SDP technique is employed to convert vibration signals into images for visualization. DRN enables adequate extraction of rolling bearing fault characteristics and prevents training difficulties and gradient vanishing in deep level networks. CBAM assists the diagnostic model in concentrating on the image’s more distinctive parts and preventing the interference of non-featured parts. Finally, the method’s validity was tested with a composite fault dataset of motor bearings containing multiple loads and fault diameters. The experimental results reflect that the presented approach can attain a diagnostic precision of over 99% and good stability and generalization.https://www.mdpi.com/1424-8220/22/24/9954rolling bearingsintelligent fault diagnosissymmetrized dot pattern (SDP)deep residual network (DRN)attention mechanisms |
| spellingShingle | Wei Cui Guoying Meng Tingxi Gou Aiming Wang Rui Xiao Xinge Zhang Intelligent Rolling Bearing Fault Diagnosis Method Using Symmetrized Dot Pattern Images and CBAM-DRN Sensors rolling bearings intelligent fault diagnosis symmetrized dot pattern (SDP) deep residual network (DRN) attention mechanisms |
| title | Intelligent Rolling Bearing Fault Diagnosis Method Using Symmetrized Dot Pattern Images and CBAM-DRN |
| title_full | Intelligent Rolling Bearing Fault Diagnosis Method Using Symmetrized Dot Pattern Images and CBAM-DRN |
| title_fullStr | Intelligent Rolling Bearing Fault Diagnosis Method Using Symmetrized Dot Pattern Images and CBAM-DRN |
| title_full_unstemmed | Intelligent Rolling Bearing Fault Diagnosis Method Using Symmetrized Dot Pattern Images and CBAM-DRN |
| title_short | Intelligent Rolling Bearing Fault Diagnosis Method Using Symmetrized Dot Pattern Images and CBAM-DRN |
| title_sort | intelligent rolling bearing fault diagnosis method using symmetrized dot pattern images and cbam drn |
| topic | rolling bearings intelligent fault diagnosis symmetrized dot pattern (SDP) deep residual network (DRN) attention mechanisms |
| url | https://www.mdpi.com/1424-8220/22/24/9954 |
| work_keys_str_mv | AT weicui intelligentrollingbearingfaultdiagnosismethodusingsymmetrizeddotpatternimagesandcbamdrn AT guoyingmeng intelligentrollingbearingfaultdiagnosismethodusingsymmetrizeddotpatternimagesandcbamdrn AT tingxigou intelligentrollingbearingfaultdiagnosismethodusingsymmetrizeddotpatternimagesandcbamdrn AT aimingwang intelligentrollingbearingfaultdiagnosismethodusingsymmetrizeddotpatternimagesandcbamdrn AT ruixiao intelligentrollingbearingfaultdiagnosismethodusingsymmetrizeddotpatternimagesandcbamdrn AT xingezhang intelligentrollingbearingfaultdiagnosismethodusingsymmetrizeddotpatternimagesandcbamdrn |